A recurrent neural network for real-time matrix inversion

Jun Wang

Research output: Contribution to journalArticlepeer-review

111 Citations (Scopus)

Abstract

A recurrent neural network for computing inverse matrices in real-time is proposed. The proposed recurrent neural network consists of n independent subnetworks where n is the order of the matrix. The proposed recurrent neural network is proven to be asymptotically stable and capable of computing large-scale nonsingular inverse matrices in real-time. An op-amp based analog neural network is discussed. The operating characteristics of the op-amp based analog neural network is also demonstrated via an illustrative example.

Original languageEnglish
Pages (from-to)89-100
Number of pages12
JournalApplied Mathematics and Computation
Volume55
Issue number1
DOIs
Publication statusPublished - Apr 1993
Externally publishedYes

Fingerprint

Dive into the research topics of 'A recurrent neural network for real-time matrix inversion'. Together they form a unique fingerprint.

Cite this